Viewpoint Of Learning Research Articles

A Review of Traditional Methods and Deep Learning for Face Recognition

Face recognition technology is a key research direction in artificial intelligence and computer vision. It first originated in the 1960s, when Bledsoe et al. proposed and studied computer programming based on face recognition. It is divided into three steps: face detection, feature extraction, and face verification. This paper briefly introduces the wide application of face recognition in various fields such as vulnerable groups, analyses its characteristics and progress from the viewpoints of traditional learning and deep learning, and focuses on the methods based on face feature extraction (including geometric features, texture features, local features, etc.). From the previous studies appear some problems connected to environmental changes, such as light change, facial occlusion, posture and privacy leakage, etc. This paper will give the possible reasons for these problems and give the possible development direction of the future by exploring the current face recognition technology to provide a reference for the related research of face recognition technology.

EAV: EEG-Audio-Video Dataset for Emotion Recognition in Conversational Contexts

Understanding emotional states is pivotal for the development of next-generation human-machine interfaces. Human behaviors in social interactions have resulted in psycho-physiological processes influenced by perceptual inputs. Therefore, efforts to comprehend brain functions and human behavior could potentially catalyze the development of AI models with human-like attributes. In this study, we introduce a multimodal emotion dataset comprising data from 30-channel electroencephalography (EEG), audio, and video recordings from 42 participants. Each participant engaged in a cue-based conversation scenario, eliciting five distinct emotions: neutral, anger, happiness, sadness, and calmness. Throughout the experiment, each participant contributed 200 interactions, which encompassed both listening and speaking. This resulted in a cumulative total of 8,400 interactions across all participants. We evaluated the baseline performance of emotion recognition for each modality using established deep neural network (DNN) methods. The Emotion in EEG-Audio-Visual (EAV) dataset represents the first public dataset to incorporate three primary modalities for emotion recognition within a conversational context. We anticipate that this dataset will make significant contributions to the modeling of the human emotional process, encompassing both fundamental neuroscience and machine learning viewpoints.

Discussion On Print Game Teaching from The Viewpoint of Worldwide Literacy Learning: The Influence and Explanation on Children’s Development

The study will find ways in which print game teaching intersects with global literacy education and how the teaching of the print game impacts the development of children. The study will explore the printmaking activities that enable cognitive, social, and emotional growth for young learners. This is based on historical perspectives of development in children, methods derived in the early education of children, and games in education. The present research study identifies and underlines that the integration of global perspectives and traditional Chinese culture into print game curricula is one of the ways through which cross-cultural understanding and appreciation may be furthered. The objectives of the research, are to investigate the impact of print game teaching on cognitive development, assessment of the most innovative method of teaching global literacy-oriented print games, and how printmaking is effective in enhancing children's social and emotional intelligence. The study tries to design inclusive print game curriculums that target all kinds of learners, with a focus on diversity, and strives to inspire collaboration among the teachers in sharing best practices within their global literacy education. It will include the practical realities of print game teaching in an early childhood education setting, which is a descriptive method based on qualitative research. The expectations from the findings of this research, therefore, will be to enhance practices in early education and cultural understanding that will result in children being empowered actors in this globalized world.

Unsupervised lung CT image registration via stochastic decomposition of deformation fields

We address the problem of lung CT image registration, which underpins various diagnoses and treatments for lung diseases. The main crux of the problem is the large deformation that the lungs undergo during respiration. This physiological process imposes several challenges from a learning point of view. In this paper, we propose a novel training scheme, called stochastic decomposition, which enables deep networks to effectively learn such a difficult deformation field during lung CT image registration. The key idea is to stochastically decompose the deformation field, and supervise the registration by synthetic data that have the corresponding appearance discrepancy. The stochastic decomposition allows for revealing all possible decompositions of the deformation field. At the learning level, these decompositions can be seen as a prior to reduce the ill-posedness of the registration yielding to boost the performance. We demonstrate the effectiveness of our framework on Lung CT data. We show, through extensive numerical and visual results, that our technique outperforms existing methods.

Transformation and learning of the non-equidimensional hesitant fuzzy information based on an extended generative adversarial network

In the subjective evaluation process, the hesitant fuzzy set (HFS), as a convenient and robust presentation tool, cannot only suitably address the decision makers’ (DMs’) or experts’ hesitant and uncertain issues but also can arise the dimension curse puzzle. Furthermore, the decision-making result is just derived according to the given objective and subjective information, without considering the DM’s subjective evaluation and the environment’s dynamic influence. Unlike the previous studies, this paper tries to address them from the deep learning viewpoint. To this end, we first define the non-equidimensional HFS (NHFS) and then introduce the equidimensional and classification characters into the NHFS to further develop the equidimensional HFS (EHFS) and the EHFS with the optimal classification result. Then, the equidimensional hesitant fuzzy-generative adversarial network (EHF-GAN) model is proposed to transform the hesitant fuzzy information from the non-equidimensional to the equidimensional form. The generalization and the convergence of the new model are proven to show the models’ reasonability. In addition, the double-learning algorithm of the EHF-GAN model is designed, which can fuse the DMs’ dynamic judgments and derive the optimal decision-making results. Lastly, this paper applies the proposed model and algorithm to an illustrative example of the new smart city enterprises and then shows their feasibility and effectiveness.

Authors' Reply to the Comments by Kamata et al.

We thank Kamata et al. (2023)[1] for their interest in our work [2], and for providing an explanation of the quasi-linear kernel from a viewpoint of multiple kernel learning. In this letter, we first give a summary of the quasi-linear SVM. Then we provide a discussion on the novelty of quasi-linear kernels against multiple kernel learning. Finally, we explain the contributions of our work [2].

Promoting Academic Success and Social Inclusion in Non-Formal Education Contexts: The Case of a North-East Region of Portugal

The processes leading to school failure and early school leaving are complex and involve multidimensional factors. In Portugal, as in other European countries, in the last decade, several policies, programmes, and practices have been developed to address this issue. This article focuses on a socio-educational practice of the study support type developed within a national programme aimed at social inclusion and educational success located in the community. The data collected through a semi-structured interview and a focus group with socio-educational professionals allowed us to identify how the study support practice is characterised and perceived by these actors. Processes and factors of transformation that occurred in the practice regarding its mode of implementation, conceptual evolution, and specificities were also addressed. Results indicate that the practice promotes improvements in participants’ outcomes such as learning, social behaviour, integration, and autonomy; the construction of a strong and sustained relationship with significant adults from the learning point of view; and the completion of compulsory schooling and studies. Hence, the research findings highlight that participation in the practice leads to transformative processes in the academic pathways of children and young people involved in the practice concerning academic, individual, and social dimensions.

Suggestions for Improving Active Learning ‎Viewpoint of Arabic Teachers in Qatif Governorate ‎in Kingdom of Saudi Arabia

The present study aims to Investigate Suggestions of Arabic ‎Teachers In Qatif Governorate In Kingdom of Saudi Arabia for ‎Improving Active Learning. In order to achieve this objective ‎questionnaire was designed. consisted of (20) items distributed ‎to five Domains: curriculum, teacher, environment of school, ‎management of school, student. and sixth domain related to ‎additional suggestions from Teachers. It was distributed to the ‎study Sample which was 168Arabic teachers chosen by ‎stratified random sample from all school levels. The results of ‎the study indicate that the domain of improving teacher was the ‎first with a high degree and mean (4.20), then the domain of ‎improving environment of school with a high degree and mean ‎‎(3.89). The study recommended to improve training teachers. ‎And improving environment of school by supplying it with ‎suitable facilities and materials, and reducing numbers of ‎students in classrooms.‎ ‎(Keywords: Suggestions, Improving, Active Learning, Arabic ‎Language Teachers)‎

Multi-scale foreground-background separation for light field depth estimation with deep convolutional networks

There are three viewpoints to divide the depth from light field (DFLF) methods: light field (LF) representation, signal processing, and learning viewpoints. In the signal processing viewpoint in details, the DFLF methods can be divided into three groups: cost-based, foreground-background separation (FBS)-based, and depth model-based methods. Although the deep learning techniques are widely implemented in the cost-based and depth model-based methods for the DFLF, they are not implemented in the FBS-based method, yet. In this paper, we propose a DFLF method based on the FBS with the deep learning techniques. Based on an observation that the angular aliasing artifacts are reduced in the resulting disparity maps obtained from spatially low-scale LF images, multi-scale (MS) FBS score maps are used in the proposed methods. To combine the MS FBS score maps into a single FBS score maps, four directional LF gradients, features from the 4-D LF, and features from the center view images are utilized. Based on the sensitivity and specificity loss, the gradient matching loss between the predicted and ground truth disparity maps is used to improve the performance around the occlusion boundary in the resulting disparity maps. The experimental results show that the proposed method performs reasonably in both the synthetic and real LF datasets. Especially, in the texture-less region in the real dataset, the resulting disparity maps obtained by the proposed method show that the artifacts are reduced compared to those by the existing DFLF methods.

An animal physiology Pressbook (OER) creation process, a synergistic collaboration with undergraduates and faculty

OERs or Open Educational Resources have shown to reduce financial barriers in undergraduates by providing low cost or no cost textbooks. However, the potential OER textbooks available for a three-hundred level Biological Sciences and Natural Sciences majors Animal Physiology course (BIOLA310) at UAA do not align with the foundation of this course’s structure of homeostasis and core concepts in physiology. Thus an OER Pressbook was created by a former BIOLA310 undergraduate student for future students that mapped the course outline, utilizing the essential core concepts of Homeostasis, Systems Integration, and Scientific reasoning. This study explores current attitudes regarding OER usage of undergraduates enrolled in BIOLA310 as compared to undergraduates that were enrolled in Fall 2021 BIOLA310, when there was not an official OER textbook. Anonymous demographic data, including first generation student and pell grant status will be collected for all participants to explore any potential differences in OER impression based on student resources. Data will also be collected regarding the informational component of the OER pressbook that students engage with the most. Hypothesis: Students connected more directly with the material of the undergraduate created Pressbook OER’s, as compared to a previous version of instructor curated OER materials in Fall 2021, due to low cost, the information presented from a near peer, and how the textbook was designed for the course. Data will be collected by an anonymous qualtrics survey to protect the identity of the volunteers. Pressbooks, the web host of the Animal Physiology OER gathers Key Performance Indicators (KPIs) and tracks relevant metrics, to compare student perception of use to actual use of the materials. Data will be analyzed to assess usage evaluated by financial barriers and perceived inclination due to the OER being designed by a fellow student. Supporting student learning from diverse perspectives, OER’s created with content expert faculty and undergraduate student interpretation might increase OER availability. By lowering the barrier of OER creation, then potentially more curated resources are created that resonate with near peer learning that will increase the diversity of learning viewpoints to support undergraduate students. Research reported in this publication was supported by an Institutional Development Award (IDeA) from the National Institute of General Medical Sciences of the National Institutes of Health under grant number P20GM103395. This is the full abstract presented at the American Physiology Summit 2023 meeting and is only available in HTML format. There are no additional versions or additional content available for this abstract. Physiology was not involved in the peer review process.

Generative Models as an Emerging Paradigm in the Chemical Sciences.

Traditional computational approaches to design chemical species are limited by the need to compute properties for a vast number of candidates, e.g., by discriminative modeling. Therefore, inverse design methods aim to start from the desired property and optimize a corresponding chemical structure. From a machine learning viewpoint, the inverse design problem can be addressed through so-called generative modeling. Mathematically, discriminative models are defined by learning the probability distribution function of properties given the molecular or material structure. In contrast, a generative model seeks to exploit the joint probability of a chemical species with target characteristics. The overarching idea of generative modeling is to implement a system that produces novel compounds that are expected to have a desired set of chemical features, effectively sidestepping issues found in the forward design process. In this contribution, we overview and critically analyze popular generative algorithms like generative adversarial networks, variational autoencoders, flow, and diffusion models. We highlight key differences between each of the models, provide insights into recent success stories, and discuss outstanding challenges for realizing generative modeling discovered solutions in chemical applications.

Parallel Learning: Overview and Perspective for Computational Learning Across Syn2Real and Sim2Real

The virtual-to-real paradigm, i.e., training models on virtual data and then applying them to solve real-world problems, has attracted more and more attention from various domains by successfully alleviating the data shortage problem in machine learning. To summarize the advances in recent years, this survey comprehensively reviews the literature, from the viewport of parallel intelligence. First, an extended parallel learning framework is proposed to cover main domains including computer vision, natural language processing, robotics, and autonomous driving. Second, a multi-dimensional taxonomy is designed to organize the literature in a hierarchical structure. Third, the related virtual-to-real works are analyzed and compared according to the three principles of parallel learning known as description, prediction, and prescription, which cover the methods for constructing virtual worlds, generating labeled data, domain transferring, model training and testing, as well as optimizing the strategies to guide the task-oriented data generator for better learning performance. Key issues remained in virtual-to-real are discussed. Furthermore, the future research directions from the viewpoint of parallel learning are suggested.

Error Analysis of Regularized Trigonometric Linear Regression With Unbounded Sampling: A Statistical Learning Viewpoint

Error Analysis of Regularized Trigonometric Linear Regression With Unbounded Sampling: A Statistical Learning Viewpoint

Optimizing patient recruitment into clinical trials of antimicrobial-resistant pathogens.

Recruitment of patients with critical priority antimicrobial-resistant (AMR) bacteria into drug approval randomized controlled trials (RCTs) has not been successful to date. Approaching from the viewpoint of clinician-investigators and learning from the experience of AMR-focused investigator-initiated trials, we present suggestions to improve feasibility and efficiency of RCTs evaluating patients with severe infections caused by carbapenem-resistant Gram-negative or other AMR bacteria. Considerations address the trials' eligibility criteria, whether the focus of the trial is pathogen- or syndrome-targeted, trials' case report forms and monitoring, informed consent strategies for the recruitment of extremely ill patients, team dedication and incentives to run the trial and alternative trial designs. Evidence on the effects of new drugs against the AMR that these drugs target is weak and needs to be improved through better industry-academic collaboration, taking advantage of the different strengths of industry-led and investigator-initiated research.

Adaptive discrimination between harmful and harmless antigens in the immune system by predictive coding

The immune system discriminates between harmful and harmless antigens based on past experiences; however, the underlying mechanism is largely unknown. From the viewpoint of machine learning, the learning system predicts the observation and updates the prediction based on prediction error, a process known as "predictive coding." Here, we modeled the population dynamics of Tcells by adopting the concept of predictive coding; conventional and regulatory Tcells predict the antigen concentration and excessive immune response, respectively. Their prediction error signals, possibly via cytokines, induce their differentiation to memory Tcells. Through numerical simulations, we found that the immune system identifies antigen risks depending on the concentration and input rapidness of the antigen. Further, our model reproduced history-dependent discrimination, as in allergy onset and subsequent therapy. Taken together, this study provided a novel framework to improve our understanding of how the immune system adaptively learns the risks of diverse antigens.

Transfer Relation Network for Fault Diagnosis of Rotating Machinery With Small Data.

Many deep-learning methods have been developed for fault diagnosis. However, due to the difficulty of collecting and labeling machine fault data, the datasets in some practical applications are relatively much smaller than the other big data benchmarks. In addition, the fault data come from different machines. Therefore, on some occasions, fault diagnosis is a multidomain problem with small data, where satisfactory transfer performance is difficult to obtain and has been rarely explored from the few-shot learning viewpoint. Different from the existing deep transfer learning solutions, a novel transfer relation network (TRN), combining a few-shot learning mechanism and transfer learning, is developed in this study. Specifically, the fault diagnosis problem has been treated as a similarity metric-learning problem instead of solely feature weighted classification. A feature net and a relation net have been, respectively, constructed for feature extraction and relation computation. The Siamese structure has been borrowed to extract the features of the source and the target domain samples with shared weights. Multikernel maximum mean discrepancy (MK-MMD) is employed on several higher layers with different tradeoff parameters to enable an efficient domain feature transfer considering different feature properties. To implement efficient diagnosis based on small data, an episode-based few-shot training strategy is adopted to train TRN. Average pooling has been adopted to suppress the noise influence from the vibration sequence which turns out to be important for the success of time sequence-based fault diagnosis. Transfer experiments on four datasets have verified the superior performance of TRN. A significant improvement of classification accuracy has been made compared with the state-of-the-art methods on the adopted datasets.

Deep-learning prediction and uncertainty quantification for scramjet intake flowfields

Scramjet is a promising propulsion technology that provides efficient and flexible access-to-space and high-speed point-to-point transportation. Since the design process of scramjet (supersonic combustion ramjet) engines requires numerous flowfield evaluations, fast and accurate flow predictions play a key role in promoting the development of knowledge and technologies. Deep learning techniques are increasingly used for flow prediction, and the present study applies them to viscous supersonic flowfields inside scramjet intakes. The capability and limitations of deep learning prediction for such flowfields have been investigated from the viewpoints of both physics and machine learning by means of uncertainty quantification and principal component analysis. The results indicate that the flowfields with complex aerodynamic phenomena such as boundary layer separation and Mach disks are difficult to predict. It has been attributed to lack of similar flowfields as well as the sensitivity of the fluid phenomena to the geometries. Uncertainty quantification effectively allows for the detection of such difficult cases without model verification prior to utilization. It has been further employed to address the issues in the prediction of flowfields with boundary-layer separations by increasing the number of training data effectively.

A STUDY OF COMPETENCE MODEL FOR FIVE-YEAR JUNIOR COLLEGE STUDENTS TAKING INTERNSHIP IN HAIRDRESSING INDUSTRY

The paper aims to analyze the competence model for vocational college students taking internship in hairdressing industry based on the viewpoints of learning by doing, based on the discourses from Dewey’s experience theory and to understand the correlation and hierarchy of the context of competence for the professional skills of hairdressing industry, thereby to facilitate the design and development of human resources for the hairdressing industry. The study analyzes the off-campus interns for junior college cosmetology andhairdressing related departments in Taiwan. The study also emphasizes on school teachers, hairdressing personnel and hairdressing industry interns through conducting qualitative research document analysis, and quantitative research ISM system. The analysis of context and correlation of competence skills for hairdressing industry can be adopted as the standard of occupational information for designing hairdressing competence and learning map by schools and vocational institutes. Secondly, the study will link hairdressing personnel development with hairdressing industry demand to create win-win situations for school course instrument, industry education training and employment of industry personnel.

Teachers' and Parents' Viewpoints of Game-Based Learning: An Exploratory Study

During the recent global pandemic, children’s screen time has been raised due to learning at home programs. Unexpectedly, teachers and parents have been forced to adapt to digital learning technology for children’s education. This study aimed to explore the anxiety and dilemmas faced by teachers and parents in using game-based digital learning. The researcher argues that their role as educators and facilitators in digital learning and playing activity is critical. It is essential to understand how they view, deal with, and experience game-based learning before developing an educational game. A gap was found in the existing studies about teachers’ and parents’ perspectives of game-based learning. Two questionnaires were developed separately for teachers and parents of primary school children in East Java, Indonesia. The results provided information about the teachers’ and parents’ concerns about digital learning, including their frustrations and motivations.
 Keywords: game design, game-based learning, educational game, digital learning, human-centered design

A Qualitative Study on Married Migrant Women’s Experience of Participation in Self-help Groups from the Perspective of Transformative Learning

This study examined self-help groups for married migrant women which have not been discussed from the viewpoint of learning from the perspective of transformative learning and tried to suggest the direction of self-help groups. For this, the research question was set as 'What does married migrant women's experience of participation in self-help groups from the perspective of transformative learning?'. For the study, data were collected by arranging in-depth interviews with 7 married migrant women who participated in self-help groups for more than 2 years in the B Family Center in A City. And based on this, the in-depth meanings in the experience were analyzed. Based on the collected data, each three central meanings were drawn from the categories of experience by conversion stage, the level of conversion and introspection, and the results of the conversion. Married migrant women planned and attempted a meaning life by experiencing dilemmas and experienced problem solving through sympathy and cooperation in their self-help groups. It has found that the level of conversion and introspection appeared in the form of self-awareness, professional competency development, and introspection as migrant women and the results of the conversion appeared in the domain of individuals, families, and society. The above research results show that self-help groups promote the shift in married migrant women's perspectives and become the learning center that they can be expanded to indivisual and social growth. Based on the results of the study, it found educational implications of self-help groups for married migrant women and sought the direction for their development.